master
bugfix: Aligned faces. Fix padding calculation
Replace imageio with pyav/ffmpeg-binaries (#1534)
bugfix: Manual tool - prevent error on no masks
Alignments: Migrate typed-dicts to dataclasses
bugfix: Inference model. Make more robust to esoteric layouts
convert bugfixes: - ffmpeg writer: Exit audio buffer when no audio available - convert: correctly apply y-offset - Fix color adjust when "none" selected
Train: Migrate data loading to Torch (#1540)
Adding tools.py as main script for using tools, as well as integrating all feature requests from #255 and #278 (#298)